Most outdoor visual surveillance scenes involve objects of interest moving on the ground plane. However, perspective distortion introduces many difficulties to various applicatio...
Traditionally, human facial expressions have been studied using either 2D static images or 2D video sequences. The 2D-based analysis is incapable of handing large pose variations....
Lijun Yin, Xiaozhou Wei, Yi Sun, Jun Wang, Matthew...
Face-to-face meetings usually encompass several modalities including speech, gesture, handwriting, and person identification. Recognition and integration of each of these modaliti...
Michael Bett, Ralph Gross, Hua Yu, Xiaojin Zhu, Yu...
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
Abstract. Motion capture, a currently active research area, needs estimation of the pose of the subject. This requires a match between a model and the 3D shape, constructed using a...